| Model Type | 
  | 
| LLM Name | Meta Llama 3 Instruct 120B Cat A Llama | 
| Repository ๐ค | https://huggingface.co/gbueno86/Meta-Llama-3-Instruct-120b-Cat-a-llama | 
| Model Size | 120b | 
| Required VRAM | 243.9 GB | 
| Updated | 2025-09-23 | 
| Maintainer | gbueno86 | 
| Model Type | llama | 
| Instruction-Based | Yes | 
| Model Files | |
| Model Architecture | LlamaForCausalLM | 
| Context Length | 8192 | 
| Model Max Length | 8192 | 
| Transformers Version | 4.40.1 | 
| Tokenizer Class | PreTrainedTokenizerFast | 
| Vocabulary Size | 128256 | 
| Torch Data Type | bfloat16 | 
Model  | 
            Likes  | 
            Downloads  | 
            VRAM  | 
        
|---|---|---|---|
| ...t 120B Cat A Llama EXL2 5.5bpw | 0 | 5 | 85 GB | 
| ...t 120B Cat A Llama EXL2 4.5bpw | 1 | 4 | 70 GB | 
Best Alternatives  | 
        Context / RAM  | 
        Downloads  | 
        Likes  | 
    
|---|---|---|---|
| Meta Llama 3 225B Instruct | 8K / 443.2 GB | 7 | 18 | 
| ...0B Instruct Abliterated Merged | 8K / 243.7 GB | 17 | 1 | 
| Koishi 120B Qlora | 4K / 216.9 GB | 6 | 1 | 
| ...t 120B Cat A Llama EXL2 5.5bpw | 8K / 85.3 GB | 5 | 0 | 
| ...t 120B Cat A Llama EXL2 4.5bpw | 8K / 70.3 GB | 4 | 1 | 
| ...egaDolphin 120B 2.9bpw H6 EXL2 | 4K / 44.3 GB | 7 | 3 | 
| ...gaDolphin 120B 2.65bpw H6 EXL2 | 4K / 40.5 GB | 7 | 2 | 
| ...egaDolphin 120B 4.0bpw H6 EXL2 | 4K / 60.8 GB | 6 | 1 | 
| MegaDolphin 120B GPTQ | 4K / 61.1 GB | 8 | 4 | 
| MegaDolphin 120B AWQ | 4K / 63.3 GB | 6 | 2 | 
๐ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐